Base model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit (loaded in 4-bit for training via Unsloth)
Adapter type: LoRA, rank 16, alpha 16, dropout 0, targeting all attention and MLP projection layers (q/k/v/o_proj, gate/up/down_proj)
Training framework: Unsloth FastLanguageModel + TRL SFTTrainer
Training data: Harsh-k-007/fitcoach-conversations — 1,407 synthetic coaching conversations (95/5 train/eval split for this run)
Sequence length: 1536 tokens, with sequence packing (bfd strategy)
Precision: bf16 training on a single T4 GPU (Google Colab free tier)
Epochs: 2, effective batch size 8 (1 × 8 grad accumulation), cosine LR schedule, peak LR 2e-4

Intended Use

FitCoach is a conversational intake coach for fitness and nutrition. Given a user's goal, it asks one question at a time to gather the relevant context, then generates a structured plan.

Scope is intentionally narrow:

Meal plans (~60% of training data): collects goal, age/height/weight, dietary restrictions, activity level
Workout plans (~40% of training data): collects goal, experience level, days per week, equipment access

Out of scope

Injuries, medical conditions, or any medical advice
Macro/calorie arithmetic — the model can describe macro targets conceptually but is not reliable at computing them; treat any numeric macro breakdown as approximate, not verified
Unprompted macro generation — the model does not currently generate macros unless explicitly asked (known dataset gap, planned for v2)

How to Use

The adapter was trained against a 4-bit base, but at deployment it's loaded against the full-precision instruct model — QLoRA adapters are compatible with the full-precision version of the same architecture, and this avoids requiring bitsandbytes at inference time.

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model_id = "unsloth/Meta-Llama-3.1-8B-Instruct"
adapter_id = "Harsh-k-007/fitcoach-8b-adapter"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
tokenizer.pad_token = "<|finetune_right_pad_id|>"

base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    dtype=torch.float16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()

messages = [
    {"role": "system", "content": "You are FitCoach, a friendly fitness and nutrition coach."},
    {"role": "user", "content": "Build me a 4-day gym workout plan for muscle gain."},
]

encoded = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
input_ids = encoded["input_ids"] if hasattr(encoded, "keys") else encoded
input_ids = input_ids.to(model.device)

output = model.generate(
    input_ids,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    pad_token_id=128004,
)
print(tokenizer.decode(output[0][input_ids.shape[-1]:], skip_special_tokens=True))

Training Procedure

Method: Supervised fine-tuning (SFT) with TRL SFTTrainer, using Unsloth's FastLanguageModel for memory-efficient LoRA training (gradient checkpointing via use_gradient_checkpointing="unsloth")
Loss: full-conversation loss (train_on_responses_only / assistant-only masking was not applied in this run — a documented future optimization once reliably supported for the Llama 3 chat template)
Chat template: Llama 3.1 (unsloth.chat_templates.get_chat_template)
Optimizer: adamw_8bit, weight decay 0.01, cosine schedule, 10 warmup steps
Hardware: Google Colab T4 (free tier), with Drive checkpointing for resumability across the 90-minute idle / 12-hour session limits

Known Limitations

Macro arithmetic is hallucinated. The model isn't reliable at computing calorie/macro numbers. A v2 release plans to add a calculator/tool layer for this.
Macros aren't generated unprompted. The dataset under-represents this, so the model needs to be asked explicitly. Planned fix for v2 via dataset augmentation.
No assistant-only loss in this training run (see above).

Citation

If you use this model, please link back to this repo and the training dataset.